Agentic AI Engineer

Link Group; Warszawa; Hybrid; PLN 180,000 - 260,000; Full time

Job summary

Link Group is seeking an AI/LLM expert to architect and deploy agentic systems at scale. You will design RAG pipelines, build agent/tool ecosystems, and optimize prompts and context strategies for high-precision results.

You will evaluate models with robust benchmarks, monitor production latency, and translate cutting-edge AI research into practical product enhancements.

Qualifications

• Hands-on experience with Python, SQL and Git version control.
• Proven prompt engineering, context engineering, and RAG pattern design.
• Experience with LLM evaluation frameworks, benchmarks, and error analysis.
• Production deployment of LLM applications, observability, tracing, and cost monitoring.
• Ability to translate AI research into practical product enhancements.

Responsibilities

• Architect, build, and optimize autonomous AI agents and tool ecosystems.
• Design and refine RAG pipelines, prompts, and context-window strategies.
• Deploy and monitor LLM applications in production with observability.
• Evaluate models, benchmarks, and perform systematic error analysis.
• Translate recent AI research into tangible product improvements.

Skills

Python

SQL

Git

AI

RAG

LLM

English

Agentic AI

Evaluation

LLMOps

Observability

Software Eng

Context Engineering

Tools

Python

SQL

Git

Job description

• Python
• SQL
• Git
• AI
• RAG
• LLM
• Angielski
• Programming Proficiency: High proficiency in Python, SQL, and Git version control.
• Agentic AI Expertise: Proven experience in prompt engineering, context engineering, RAG patterns, and designing agent/tool ecosystems.
• Evaluation & Optimization: Hands-on experience with LLM evaluation frameworks, benchmark design, model selection, and systematic error analysis.
• Production Deployment & LLMOps: Practical experience deploying LLM applications, including observability, tracing, cost monitoring, and latency tuning.
• Research-to-Product Mindset: Demonstrated ability to dissect recent AI papers and open-source breakthroughs and apply them directly to software products.
• Agentic Systems & Tool Design: Architect, build, and optimize autonomous AI agents, tool integration frameworks, skills, and multi-step agentic workflows.
• Context Engineering & RAG: Design and refine advanced Retrieval-Augmented Generation (RAG) pipelines, system prompts, and context-window strategies for maximum accuracy and efficiency.
• AI Research & Innovation: Stay at the forefront of cutting-edge AI/LLM research and translate emerging methodologies into practical product enhancements.
• Model Evaluation & Error Analysis: Conduct systematic model selection, benchmarks, and granular error analysis to continuously improve output quality and mitigate hallucinations.
• LLMOps & Observability: Deploy, monitor, and maintain LLM applications in production; implement telemetry, logging, and performance tracking to ensure system reliability.
• Software Engineering: Write scalable, clean, and maintainable code, maintaining repository best practices and version control workflows.
• Start ASAP

We're a bunch of super-dedicated and passionate people who truly believe in making a difference and delivering amazing results on a huge scale.

We're the real deal when it comes to expertise:

We've got a whopping 100,000 IT specialists in our network

73% of our experts are seasoned pros with over 8 years of experience

78% of the specialists in our network have at least 2 years of experience working in distributed teams

And get this, we conduct 99% of our candidate interviews online and fromafar.

Join the group of high-performing tech consultants